Member of Technical Staff - RL Training Framework (Reinforcement Learning)

TL;DR

Member of Technical Staff - RL Training Framework (Reinforcement Learning): Building and operating the RL training framework systems for everything from small ablations to production training runs with an accent on end-to-end training performance profiling, debugging, and optimization. Focus on improving scalability and observability of the RL stack while working across the full stack.

Location: Palo Alto, CA

Salary: $180,000 - $440,000 USD

Company

SpaceXAI builds AI systems to understand the universe and support humanity’s pursuit of knowledge.

What you will do

• Design and implement systems that back all RL workloads, from small-scale experiments to production training runs.
• Profile, debug, and optimize end-to-end RL training performance.
• Improve scalability and observability across the RL training stack.

Requirements

• Experience building, debugging, and optimizing efficiency of large-scale distributed systems.
• Ability to dive into unfamiliar areas and solve problems across all levels of the stack.
• Proficiency in Python, Jax, Rust, and/or C++.
• Strong communication skills to concisely and accurately share knowledge with teammates.

Nice to have

• Experience with large-scale LLM training infrastructure.
• Strong knowledge of reinforcement learning techniques.
• Experience with RL numerics.

Culture & Benefits

• Small, highly motivated team with a flat organizational structure.
• Hands-on expectations with direct contribution to the company mission.
• Equity and comprehensive medical, vision, and dental coverage.
• 401(k) retirement plan plus short- and long-term disability insurance and life insurance.
• 401(k) access and various additional discounts and perks.